# Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network

arXiv: https://arxiv.org/abs/1608.02214 · HTML: https://mlsanity.com/paper/1608.02214/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2016.

## Built on by (most cited first, 18 of 18)

- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [Robust Open-Vocabulary Translation from Visual Text Representations](https://mlsanity.com/paper/2104.08211/) (2021)
- [Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPT](https://mlsanity.com/paper/2210.04186/) (2022)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise](https://mlsanity.com/paper/2109.06772/) (2021)
- [Misspelling Correction with Pre-trained Contextual Language Model](https://mlsanity.com/paper/2101.03204/) (2021)
- [CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing](https://mlsanity.com/paper/2106.06004/) (2021)
- [DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2404.14890/) (2024)
- [Sometimes We Want Translationese](https://mlsanity.com/paper/2104.07623/) (2021)
- [Misspellings in Natural Language Processing: A survey](https://mlsanity.com/paper/2501.16836/) (2025)
- [MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification](https://mlsanity.com/paper/2406.13066/) (2024)
- [TiSpell: A Semi-Masked Methodology for Tibetan Spelling Correction covering Multi-Level Error with Data Augmentation](https://mlsanity.com/paper/2505.08037/) (2025)
- [Reformulation is All You Need: Addressing Malicious Text Features in DNNs](https://mlsanity.com/paper/2502.00652/) (2025)
- [CipherSniffer: Classifying Cipher Types](https://mlsanity.com/paper/2306.08116/) (2023)
- [Finite-context Indexing of Restricted Output Space for NLP Models Facing Noisy Input](https://mlsanity.com/paper/2310.14110/) (2023)
- [Typoglycemia under the Hood: Investigating Language Models' Understanding of Scrambled Words](https://mlsanity.com/paper/2510.21326/) (2025)
- [LMSpell: Spell Correction with Pre-Trained Language Models](https://mlsanity.com/paper/2512.05414/) (2025)
- [Beyond Detection: Ethical Foundations for Automated Dyslexic Error Attribution](https://mlsanity.com/paper/2604.01853/) (2026)

## Abstract (arXiv)

Language processing mechanism by humans is generally more robust than computers. The Cmabrigde Uinervtisy (Cambridge University) effect from the psycholinguistics literature has demonstrated such a robust word processing mechanism, where jumbled words (e.g. Cmabrigde / Cambridge) are recognized with little cost. On the other hand, computational models for word recognition (e.g. spelling checkers) perform poorly on data with such noise. Inspired by the findings from the Cmabrigde Uinervtisy effect, we propose a word recognition model based on a semi-character level recurrent neural network (scRNN). In our experiments, we demonstrate that scRNN has significantly more robust performance in word spelling correction (i.e. word recognition) compared to existing spelling checkers and character-based convolutional neural network. Furthermore, we demonstrate that the model is cognitively plausible by replicating a psycholinguistics experiment about human reading difficulty using our model.